Systems and methods for 3d model based drone flight planning and control

Abstract

A method for controlling a plurality of drones to survey a location, the method comprising, at a computing system: automatically generating preliminary flight plans for a plurality of drones to survey the location based on a 3D model; receiving survey data from the plurality of drones as the plurality of drones are surveying the location based on the preliminary flight plans; updating the 3D model based on the survey data received from the plurality of drones; and automatically updating at least a portion of the flight plans based on the updated 3D model.

1 . A method for controlling a plurality of drones to survey a location, the method comprising, at a computing system:
 generating flight plans for a plurality of drones to survey the location based on a 3D model, wherein the flight plans are generated based on a desired level of image resolution of one or more objects in the location;   controlling the plurality of drones to survey the location based on the flight plans;   receiving survey data from the plurality of drones;   updating the 3D model based on the survey data received from the plurality of drones;   updating the flight plans based on the updated 3D model; and   controlling the plurality of drones to survey the location based on the updated flight plans.   
     
     
         2 . The method of  claim 1 , wherein the survey data comprises images of the location. 
     
     
         3 . The method of  claim 2 , wherein the images capture survey markers that comprise encoded location information. 
     
     
         4 . The method of  claim 1 , wherein the survey data comprises positional data for the drones. 
     
     
         5 . The method of  claim 1 , wherein the flight plans comprise a set of splines, a set of waypoints, or a combination thereof. 
     
     
         6 . The method of  claim 1 , wherein the flight plans are generated using a machine learning model that comprises an objective function that comprises a weighting of drone flight time, drone wireless signal strength, and drone battery use. 
     
     
         7 . The method of  claim 1 , comprising:
 receiving an indication from at least one drone of a detection of at least one person; and   updating a flight plan of the at least one drone to avoid flying over the at least one person.   
     
     
         8 . The method of  claim 1 , comprising:
 predicting illumination of at least one object based on the 3D model; and   updating the flight plans for the plurality of drones surveying the at least one object based on the predicted illumination.   
     
     
         9 . The method of  claim 1 , comprising:
 prior to generating the flight plans for the plurality of drones, selecting the plurality of drones from a set of available drones based on known features of the location.   
     
     
         10 . The method of  claim 1 , wherein a first object in the location is imaged at a higher resolution than a second object in the location. 
     
     
         11 . The method of  claim 1 , wherein the desired level of image resolution of the one or more objects in the location is determined based on semantic segmentation of an image of the location. 
     
     
         12 . The method of  claim 1 , wherein controlling the plurality of drones to survey the location based on the flight plans comprises controlling the plurality of drones to detect anomalies in the location. 
     
     
         13 . The method of  claim 12 , wherein updating the 3D model based on the survey data received from the plurality of drones comprises annotating the 3D model with the detected anomalies. 
     
     
         14 . The method of  claim 12 , wherein the detected anomalies comprise rust, cracks, or exposed metal. 
     
     
         15 . The method of  claim 1 , wherein controlling the plurality of drones to survey the location based on the flight plans comprises controlling the plurality of drones to scan the radio frequency signal strength of the location. 
     
     
         16 . The method of  claim 1 , wherein the survey data is received from the plurality of drones continuously as the plurality of drones are surveying the location. 
     
     
         17 . The method of  claim 1 , wherein the survey data is received from the plurality of drones periodically. 
     
     
         18 . The method of  claim 1 , comprising updating the flight plans based on weather conditions. 
     
     
         19 . A system comprising a base station communicatively coupled to a plurality of drones, the base station comprising one or more processors, memory, and one or more programs stored in the memory for execution by the one or more processors for:
 generating flight plans for a plurality of drones to survey the location based on a 3D model, wherein the flight plans are generated based on a desired level of image resolution of one or more objects in the location;   controlling the plurality of drones to survey the location based on the flight plans;   receiving survey data from the plurality of drones;   updating the 3D model based on the survey data received from the plurality of drones;   updating the flight plans based on the updated 3D model; and   controlling the plurality of drones to survey the location based on the updated flight plans.   
     
     
         20 . A non-transitory compute readable medium comprising instructions that, when executed by one or more processors of a computing system, cause the computing system to:
 generate flight plans for a plurality of drones to survey the location based on a 3D model, wherein the flight plans are generated based on a desired level of image resolution of one or more objects in the location;   control the plurality of drones to survey the location based on the flight plans;   receive survey data from the plurality of drones;   update the 3D model based on the survey data received from the plurality of drones;   update the flight plans based on the updated 3D model; and   control the plurality of drones to survey the location based on the updated flight plans.